© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11635
    Prev
    Next
    INDEX
    Explanations

    phrase or clauses after "not" or "the" or "First"

    np_acts-logits-general · gemini-2.5-flash-lite

    least, but, should, attacker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     肩
    0.50
     Handlung
    0.50
    ul
    0.49
     Emulator
    0.48
     Thun
    0.47
    zam
    0.46
     那
    0.46
    lor
    0.45
    lz
    0.45
     士
    0.45
    POSITIVE LOGITS
    訒
    0.50
     shrunk
    0.49
     کرام
    0.46
     cryptic
    0.46
    ونی
    0.46
    قبل
    0.45
    Valentines
    0.45
    ARIOS
    0.45
    کر
    0.44
    收拾
    0.44
    Activations Density 0.000%

    No Known Activations